{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T20:07:26Z","timestamp":1779739646576,"version":"3.53.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP25K15174"],"award-info":[{"award-number":["JP25K15174"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3694039","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:47:23Z","timestamp":1779133643000},"page":"75674-75689","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Fashion Feature Embedding for Global, Local, and Contextual Analysis in Fashion Social Media Popularity Prediction"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9579-2125","authenticated-orcid":false,"given":"Shun","family":"Okamoto","sequence":"first","affiliation":[{"name":"Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9136-8297","authenticated-orcid":false,"given":"Satoshi","family":"Iizuka","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4201-1096","authenticated-orcid":false,"given":"Kazuhiro","family":"Fukui","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356062"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416274"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612845"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01290"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00787"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803587"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_37"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01443"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00262"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.89"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01323"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591690"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613853"},{"key":"ref17","volume-title":"WEAR","year":"2026"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964335"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/427"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3036690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551568"},{"key":"ref24","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. NeurIPS","author":"Prokhorenkova"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref26","first-page":"6639","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. NeurIPS","author":"Ke"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803461"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5220\/0011768500003393"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654958"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00107"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27885"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123394"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3531017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2876822"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23052-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43148-7_21"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3115658"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110791"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730050"},{"key":"ref46","article-title":"FashionM3: Multimodal, multitask, and multiround fashion assistant based on unified vision-language model","author":"Pang","year":"2025","journal-title":"arXiv:2504.17826"},{"key":"ref47","article-title":"Integrating domain knowledge into large language models for enhanced fashion recommendations","author":"Shi","year":"2025","journal-title":"arXiv:2502.15696"},{"key":"ref48","article-title":"From pixels to posts: Retrieval-augmented fashion captioning and hashtag generation","author":"Umer Gondal","year":"2025","journal-title":"arXiv:2511.19149"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.716"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889957"},{"key":"ref52","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref54","article-title":"Fashion-gen: The generative fashion dataset and challenge","author":"Rostamzadeh","year":"2018","journal-title":"arXiv:1806.08317"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv:2208.01618"},{"key":"ref57","first-page":"417","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref58","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref59","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref61","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref62","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref63","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv:2203.02155"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref69","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref70","volume-title":"Clip Japanese Base","author":"Yokoo","year":"2026"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.63317\/2dwkd5xar3i5"},{"issue":"56","key":"ref72","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref74","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref75","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11522804.pdf?arnumber=11522804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:55:39Z","timestamp":1779738939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11522804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3694039","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}